Noise-resistant Deep Metric Learning with Ranking-based Instance Selection

by   Chang Liu, et al.

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains open. In this paper, we propose a noise-resistant training technique for DML, which we name Probabilistic Ranking-based Instance Selection with Memory (PRISM). PRISM identifies noisy data in a minibatch using average similarity against image features extracted by several previous versions of the neural network. These features are stored in and retrieved from a memory bank. To alleviate the high computational cost brought by the memory bank, we introduce an acceleration method that replaces individual data points with the class centers. In extensive comparisons with 12 existing approaches under both synthetic and real-world label noise, PRISM demonstrates superior performance of up to 6.06 in Precision@1.



page 5

page 13

page 14


Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering

Noisy labels are commonly found in real-world data, which cause performa...

Adaptive Hierarchical Similarity Metric Learning with Noisy Labels

Deep Metric Learning (DML) plays a critical role in various machine lear...

Improving Label Ranking Ensembles using Boosting Techniques

Label ranking is a prediction task which deals with learning a mapping b...

GMM Discriminant Analysis with Noisy Label for Each Class

Real world datasets often contain noisy labels, and learning from such d...

ExpertNet: Adversarial Learning and Recovery Against Noisy Labels

Today's available datasets in the wild, e.g., from social media and open...

Significance of Softmax-based Features in Comparison to Distance Metric Learning-based Features

The extraction of useful deep features is important for many computer vi...

Data Shapley Value for Handling Noisy Labels: An application in Screening COVID-19 Pneumonia from Chest CT Scans

A long-standing challenge of deep learning models involves how to handle...

Code Repositories



view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.